Vers un système de réalité augmentée autonome

Le concept de realite augmentee (ra) vise a accroitre la perception du monde reel en y ajoutant des elements non perceptibles a priori par l'il humain. Un des problemes majeurs qui se pose dans ce type d'etudes est de pouvoir determiner le point de vue adopte pour chaque prise de vue afin d'incruster l'objet de synthese au bon endroit. Nous proposons pour cela une methode a deux niveaux prenant en compte des appariements modele/image de courbes quelconques. Cette methode est robuste a la presence d'occultations dans l'image, ainsi qu'aux erreurs pouvant se produire lors du suivi des primitives images. Elle s'inscrit dans un systeme de recalage temporel autonome et sequentiel. Cette methode a fonctionne bien dans la plupart des cas, mais lorsque l'objet de reference est petit par rapport a la distance objet-camera, le calcul du point de vue devient moins precis. Pour pallier ce probleme, nous utilisons des appariements de points d'interet entre images consecutives de la sequence. Le point de vue de la camera est alors calcule en minimisant une fonction de cout qui tient compte a la fois des appariements modele/image de courbes et des appariements image/image de points. Enfin, nous prenons en compte les changements de parametres intrinseques de la camera qui peuvent se produire au cours de la sequence. Les methodes optimisant a la fois les parametres internes et le deplacement de la camera etant instables, nous avons opte pour un partitionnement automatique de la sequence en zooms et mouvements de camera. Les parametres de l'optimisation dependent alors du type de plan considere. Ces methodes sont validees aussi bien sur des donnees synthetiques que sur des applications en vraie grandeur, comme le projet d'illumination artificielle des ponts de Paris.

[1]  Ronald Azuma,et al.  A survey of augmented reality" Presence: Teleoperators and virtual environments , 1997 .

[2]  B. Peuchot Utilisation de détecteurs subpixels dans la modélisation d'une caméra : Vérification de l'hypothèse Sténopé , 1997 .

[3]  Kiriakos N. Kutulakos,et al.  Affine object representations for calibration-free augmented reality , 1996, Proceedings of the IEEE 1996 Virtual Reality Annual International Symposium.

[4]  Marie-Odile Berger Resolving occlusion in augmented reality: a contour based approach without 3D reconstruction , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  Jean-Claude Paul,et al.  MODELING CHARACTERISTICS OF LIGHT A METHOD BASED ON MEASURED DATA , 1994 .

[6]  D. Kriegman,et al.  On recognizing and positioning curved 3D objects from image contours , 1989, [1989] Proceedings. Workshop on Interpretation of 3D Scenes.

[7]  Marie-Odile Berger,et al.  A two-stage robust statistical method for temporal registration from features of various type , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[8]  David E. Breen,et al.  Distributed Augmented Reality for Collaborative Design Applications , 1995, Comput. Graph. Forum.

[9]  Michel Dhome,et al.  Determination of the Attitude of 3D Objects from a Single Perspective View , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  G. Toscani Systèmes de calibration et perception du mouvement en vision artificielle , 1987 .

[11]  Robert M. Haralick,et al.  Analysis and solutions of the three point perspective pose estimation problem , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Gunnar Sparr,et al.  Simultaneous reconstruction of scene structure and camera locations from uncalibrated image sequences , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[13]  Tomoyuki Nishita,et al.  A montage method: the overlaying of the computer generated images onto a background photograph , 1986, SIGGRAPH.

[14]  Luc Robert,et al.  Camera calibration without feature extraction , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[15]  Peter F. Sturm,et al.  Critical motion sequences for monocular self-calibration and uncalibrated Euclidean reconstruction , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[16]  Paul Debevec,et al.  Modeling and Rendering Architecture from Photographs , 1996, SIGGRAPH 1996.

[17]  George Drettakis,et al.  Interactive Common Illumination for Computer Augmented Reality , 1997, Rendering Techniques.

[18]  Anders Heyden,et al.  Euclidean reconstruction from image sequences with varying and unknown focal length and principal point , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[19]  Azriel Rosenfeld,et al.  Robust computer vision: a least median of squares based approach , 1989 .

[20]  Roger Y. Tsai,et al.  A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses , 1987, IEEE J. Robotics Autom..

[21]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[22]  F. A. Seiler,et al.  Numerical Recipes in C: The Art of Scientific Computing , 1989 .

[23]  Hans-Hellmut Nagel,et al.  Model-Based Object Tracking in Traffic Scenes , 1992, ECCV.

[24]  Peter F. Sturm,et al.  A Factorization Based Algorithm for Multi-Image Projective Structure and Motion , 1996, ECCV.

[25]  Andrew Zisserman,et al.  Robust parameterization and computation of the trifocal tensor , 1997, Image Vis. Comput..

[26]  Gilles Simon,et al.  Mixing synthesis and video images of outdoor environments: application to the bridges of Paris , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[27]  CohenPaul,et al.  Camera Calibration with Distortion Models and Accuracy Evaluation , 1992 .

[28]  Gilles Simon,et al.  Mixing synthetic and video images of an outdoor urban environment , 1999, Machine Vision and Applications.

[29]  Chris Harris,et al.  Tracking with rigid models , 1993 .

[30]  T. W. Maver,et al.  Visual impact analysis--Modelling and viewing the natural and built environment , 1985, Comput. Graph..

[31]  J. P. Mellor Realtime Camera Calibration for Enhanced Reality Visualization , 1995, CVRMed.

[32]  John Chung-Mong Lee,et al.  Video Annotation by Motion Interpretation Using Optical Flow Streams , 1996, J. Vis. Commun. Image Represent..

[33]  S. Bougnoux,et al.  From projective to Euclidean space under any practical situation, a criticism of self-calibration , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[34]  Marie-Odile Berger,et al.  Fully Automatic 3D/2D Subtracted Angiography Registration , 1999, MICCAI.

[35]  Marie-Odile Berger How to track efficiently piecewise curved contours with a view to reconstructing 3D objects , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[36]  Christine Chevrier,et al.  Composing Computer-generated Images and Video Films: An Application for Visual Assessment in Urban Environments , 1995, Computer Graphics.

[37]  David G. Lowe,et al.  Perceptual Organization and Visual Recognition , 2012 .

[38]  Peter F. Sturm Self-calibration of a moving zoom-lens camera by pre-calibration , 1997, Image Vis. Comput..

[39]  Vincent Lepetit,et al.  Registration methods for harmonious integration of real worlds and computer generated objects , 1999, Eurographics.

[40]  Jean-Philippe Tarel,et al.  RES: computing the interactions between real and virtual objects in video sequences , 1995 .

[41]  Tiow Seng Tan,et al.  Resolving occlusion in image sequence made easy , 1998, The Visual Computer.

[42]  Andrew Wojdala,et al.  Can Virtual Look Real? A Review of Virtual Studio Techniques , 2000, Confluence of Computer Vision and Computer Graphics.

[43]  Xinhua Zhuang,et al.  Pose estimation from corresponding point data , 1989, IEEE Trans. Syst. Man Cybern..

[44]  H. Akaike A new look at the statistical model identification , 1974 .

[45]  S. P. Mudur,et al.  Three-dimensional computer vision: a geometric viewpoint , 1993 .

[46]  Marie-Odile Berger,et al.  Registration with a zoom lens camera for augmented reality applications , 1999, Proceedings 2nd IEEE and ACM International Workshop on Augmented Reality (IWAR'99).

[47]  Takeo Kanade,et al.  Vision-Based Object Registration for Real-Time Image Overlay , 1995, CVRMed.

[48]  David G. Lowe,et al.  Integrated treatment of matching and measurement errors for robust model-based motion tracking , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[49]  Sai Ravela Tracking Object Motion Across Aspect Changes for Augmented Reality , 1996 .